coreweave-incident-runbook
Incident response runbook for CoreWeave GPU workload failures. Use when inference services are down, GPUs are unavailable, or responding to production incidents on CoreWeave. Trigger with phrases like "coreweave incident", "coreweave outage", "coreweave runbook", "coreweave service down".
Best use case
coreweave-incident-runbook is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Incident response runbook for CoreWeave GPU workload failures. Use when inference services are down, GPUs are unavailable, or responding to production incidents on CoreWeave. Trigger with phrases like "coreweave incident", "coreweave outage", "coreweave runbook", "coreweave service down".
Teams using coreweave-incident-runbook should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/coreweave-incident-runbook/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How coreweave-incident-runbook Compares
| Feature / Agent | coreweave-incident-runbook | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Incident response runbook for CoreWeave GPU workload failures. Use when inference services are down, GPUs are unavailable, or responding to production incidents on CoreWeave. Trigger with phrases like "coreweave incident", "coreweave outage", "coreweave runbook", "coreweave service down".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# CoreWeave Incident Runbook ## Triage Steps ```bash # 1. Check pod status kubectl get pods -l app=inference -o wide # 2. Check recent events kubectl get events --sort-by=.lastTimestamp | tail -20 # 3. Check node status kubectl get nodes -l gpu.nvidia.com/class -o wide # 4. Check GPU health kubectl exec -it $(kubectl get pod -l app=inference -o name | head -1) -- nvidia-smi ``` ## Common Incidents ### Inference Service Down 1. Check pod status and events 2. If OOMKilled: reduce batch size or upgrade GPU 3. If ImagePullBackOff: check registry credentials 4. If Pending: check GPU quota and availability ### GPU Node Failure 1. Pods will be rescheduled automatically 2. If no capacity: scale down non-critical workloads 3. Contact CoreWeave support for extended outages ### Model Loading Failure 1. Check HuggingFace token secret exists 2. Verify model name spelling 3. Check PVC has sufficient storage 4. Review container logs for download errors ## Rollback ```bash kubectl rollout undo deployment/inference ``` ## Resources - [CoreWeave Support](https://www.coreweave.com/support) - [CoreWeave Status](https://status.coreweave.com) ## Next Steps For data handling, see `coreweave-data-handling`.
Related Skills
responding-to-security-incidents
Assists with security incident response, investigation, and remediation. This skill is triggered when the user requests help with incident response, mentions specific incident types (e.g., data breach, ransomware, DDoS), or uses terms like "incident response plan", "containment", "eradication", or "post-incident activity". It guides the user through the incident response lifecycle, from preparation to post-incident analysis. It is useful for classifying incidents, creating response playbooks, collecting evidence, constructing timelines, and generating remediation steps. Use this skill when needing to respond to a "security incident".
runbook-creator
Runbook Creator - Auto-activating skill for Technical Documentation. Triggers on: runbook creator, runbook creator Part of the Technical Documentation skill category.
incident-response-planner
Incident Response Planner - Auto-activating skill for Security Advanced. Triggers on: incident response planner, incident response planner Part of the Security Advanced skill category.
incident-postmortem-template
Incident Postmortem Template - Auto-activating skill for Technical Documentation. Triggers on: incident postmortem template, incident postmortem template Part of the Technical Documentation skill category.
exa-incident-runbook
Execute Exa incident response with triage, mitigation, and postmortem procedures. Use when responding to Exa-related outages, investigating errors, or running post-incident reviews for Exa integration failures. Trigger with phrases like "exa incident", "exa outage", "exa down", "exa on-call", "exa emergency", "exa broken".
evernote-incident-runbook
Manage incident response for Evernote integration issues. Use when troubleshooting production incidents, handling outages, or responding to Evernote service issues. Trigger with phrases like "evernote incident", "evernote outage", "evernote emergency", "troubleshoot evernote production".
documenso-incident-runbook
Manage incident response for Documenso integration issues. Use when diagnosing production incidents, handling outages, or responding to Documenso service disruptions. Trigger with phrases like "documenso incident", "documenso outage", "documenso down", "documenso troubleshooting".
deepgram-incident-runbook
Execute Deepgram incident response procedures for production issues. Use when handling Deepgram outages, debugging production failures, or responding to service degradation. Trigger: "deepgram incident", "deepgram outage", "deepgram production issue", "deepgram down", "deepgram emergency", "deepgram 500 errors".
databricks-incident-runbook
Execute Databricks incident response procedures with triage, mitigation, and postmortem. Use when responding to Databricks-related outages, investigating job failures, or running post-incident reviews for pipeline failures. Trigger with phrases like "databricks incident", "databricks outage", "databricks down", "databricks on-call", "databricks emergency", "job failed".
coreweave-webhooks-events
Monitor CoreWeave cluster events and GPU workload status. Use when tracking pod lifecycle events, monitoring GPU utilization, or alerting on inference service health changes. Trigger with phrases like "coreweave events", "coreweave monitoring", "coreweave pod alerts", "coreweave gpu monitoring".
coreweave-upgrade-migration
Upgrade CoreWeave deployments and migrate between GPU types. Use when migrating from A100 to H100, upgrading CUDA versions, or updating inference server versions. Trigger with phrases like "upgrade coreweave", "coreweave gpu migration", "coreweave cuda upgrade", "migrate coreweave".
coreweave-security-basics
Secure CoreWeave deployments with RBAC, network policies, and secrets management. Use when hardening GPU workloads, managing model access, or configuring namespace isolation. Trigger with phrases like "coreweave security", "coreweave rbac", "secure coreweave", "coreweave secrets".